Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14392
    Prev
    Next
    INDEX
    Explanations

    verbs in past tense

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement and authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isite
    -0.76
     Recent
    -0.68
    Native
    -0.67
     Favor
    -0.66
     Improve
    -0.65
    2017
    -0.64
    2018
    -0.64
    igmatic
    -0.64
    category
    -0.63
    actionDate
    -0.63
    POSITIVE LOGITS
     proceeded
    1.42
     complied
    1.38
     promptly
    1.37
     responded
    1.33
     retali
    1.31
     reacted
    1.31
     apologized
    1.30
     retreated
    1.28
     eventually
    1.28
     hesitated
    1.27
    Activations Density 0.429%

    No Known Activations